Top-keXtremeContextualBanditswithArmHierarchyRajatSen1AlexanderRakhlin23LexingYing43RahulKidambi3DeanFoster3DanielHill3InderjitS.Dhillon53Abstract1.IntroductionMotivatedbymodernapplications,suchaso...
Self-PacedContextEvaluationforContextualReinforcementLearningTheresaEimer1Andre´Biedenkapp2FrankHutter23MariusLindauer1AbstractFigure1:ExampleinstancesoftheContextualPointMassenvironment.Theagent...
OfflineContextualBanditswithOverparameterizedModelsDavidBrandfonbrener1WilliamF.Whitney1RajeshRanganath1JoanBruna1AbstractIncontrast,thebestperformanceinmodernsupervisedlearningisoftenachievedbymas...
LeveragingGoodRepresentationsinLinearContextualBanditsMatteoPapini†1AndreaTirinzoni1MarcelloRestelli1AlessandroLazaric2MatteoPirotta2Abstractrangeofdomains,includingrecommendationsystems,on-Thelin...
AdaptingtoMisspecificationinContextualBanditswithOfflineRegressionOraclesSanathKumarKrishnamurthy1VitorHadad2SusanAthey2Abstractwhosedistributionmaydependonthecontextandaction.Theobjectiveofthealgo...
StructuredLinearContextualBandits:ASharpandGeometricSmoothedAnalysisVidyashankarSivakumar12ZhiweiStevenWu2ArindamBanerjee2Abstractselectsacontextxtitfromkavailablecontextsxt,...,xt1kBanditlearninga...
OptimalNon-parametricLearninginRepeatedContextualAuctionswithStrategicBuyerAlexeyDrutsa12Abstractsingleadvertiser(Aminetal.,2013;Mohri&Munoz,2014;Drutsa,2017b;2018;Vanunts&Drutsa,2019).Inthiscase,W...
NeuralContextualBanditswithUCB-basedExplorationDongruoZhou1LihongLi2QuanquanGu1Abstracttheexpectedrewardateachroundislinearinthefeaturevector.Whilesuccessfulinboththeoryandpractice(LiWestudythestoc...
LearningandEvaluatingContextualEmbeddingofSourceCodeAdityaKanade12PetrosManiatis2GogulBalakrishnan2KensenShi2Abstractstandtheauthor’sintentsothattheycanmaintainandextendthecode.Developersusemeanin...
HowrecurrentnetworksimplementContextualprocessinginsentimentanalysisNiruMaheswaranathan1DavidSussillo1AbstractRigorouslyunderstandinghownetworkssolveimportanttasksisacentralchallengeindeeplearning....
Bisection-BasedPricingforRepeatedContextualAuctionsagainstStrategicBuyerAntonZhiyanov12AlexeyDrutsa12AbstractMunoz,2014;Drutsa,2018)),asecond-priceauctionwithreservepricesreducestoaposted-priceauct...
BeyondUCB:OptimalandEfficientContextualBanditswithRegressionOraclesDylanJ.Foster1AlexanderRakhlin1Abstractible,generalpurposealgorithmsthatworkforarbitrary,user-specifiedclassesofpoliciesandcomewit...
TargetTrackingforContextualBandits:ApplicationtoDemandSideManagementMargauxBre´ge`re123PierreGaillard3YannigGoude12GillesStoltz2Abstractblebythedevelopmentofenergystoragedevicessuchasbatteriesorev...
ContextualMemoryTreesWenSun1AlinaBeygelzimer2HalDaume´III3JohnLangford3PaulMineiro4Abstractriessoastomaximizethedownstreamrewardofqueries.Inordertoscaletoverylargememories,ourapproachorga-Wedesign...
ContextualMulti-armedBanditAlgorithmforSemiparametricRewardModelGi-SooKim1MyungheeChoPaik1Abstract(Langfordetal.,2008),newsarticleplacementalgorithms(Lietal.,2010),revenuemanagement(Ferreiraetal.,2...
Warm-startingContextualBandits:RobustlyCombiningSupervisedandBanditFeedbackChichengZhang1AlekhAgarwal1HalDauméIII12JohnLangford1SahandNNegahban3Abstractensuringthatsuchasystemdoesnotneedtosufferto...
SemiparametricContextualBanditsAkshayKrishnamurthy1ZhiweiStevenWu1VasilisSyrgkanis2Abstractthatmakegeneralreinforcementlearningchallenging.Con-textualbanditalgorithmshaveseenrecentsuccessinappli-Th...
PracticalContextualBanditswithRegressionOraclesDylanJ.Foster1AlekhAgarwal2MiroslavDud´ık2HaipengLuo3RobertE.Schapire2Abstractagnosticinthesensethattheyareprovablyeffectiveforanygivenpolicyclassan...
ContextualGraphMarkovModel:ADeepandGenerativeApproachtoGraphProcessingDavideBacciu1FedericoErrica1AlessioMicheli1AbstractMarkovModel(Bacciuetal.,2012a)andtheconstructiveapproachofNeuralNetworkforGr...
Safety-AwareAlgorithmsforAdversarialContextualBandit122WenSunDebadeeptaDeyAshishKapoorAbstractside-effectofanewtreatmentmustbetakenintoconsidera-tionforpatients’safety.Ingeneraltheseapplicationswi...
